; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; REQUIRES: aarch64-registered-target
; RUN: opt -passes='lower-matrix-intrinsics' -mtriple=arm64-apple-iphoneos -S < %s | FileCheck %s

define <1 x float> @dotproduct_float_v6(<6 x float> %a, <6 x float> %b) {
; CHECK-LABEL: @dotproduct_float_v6(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = fmul <6 x float> [[A:%.*]], [[B:%.*]]
; CHECK-NEXT:    [[TMP1:%.*]] = call fast float @llvm.vector.reduce.fadd.v6f32(float 0.000000e+00, <6 x float> [[TMP0]])
; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <1 x float> poison, float [[TMP1]], i64 0
; CHECK-NEXT:    ret <1 x float> [[TMP2]]
;
entry:
  %c = tail call fast <1 x float> @llvm.matrix.multiply.v1f32.v6f32.v6f32(<6 x float> %a, <6 x float> %b, i32 1, i32 6, i32 1)
  ret <1 x float> %c
}

declare <1 x float> @llvm.matrix.multiply.v1f32.v6f32.v6f32(<6 x float>, <6 x float>, i32, i32, i32)

define <1 x float> @dotproduct_float_v1(<1 x float> %a, <1 x float> %b) {
; CHECK-LABEL: @dotproduct_float_v1(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = fmul <1 x float> [[A:%.*]], [[B:%.*]]
; CHECK-NEXT:    [[TMP1:%.*]] = call fast float @llvm.vector.reduce.fadd.v1f32(float 0.000000e+00, <1 x float> [[TMP0]])
; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <1 x float> poison, float [[TMP1]], i64 0
; CHECK-NEXT:    ret <1 x float> [[TMP2]]
;
entry:
  %c = tail call fast <1 x float> @llvm.matrix.multiply.v1f32.v1f32.v1f32(<1 x float> %a, <1 x float> %b, i32 1, i32 1, i32 1)
  ret <1 x float> %c
}

declare <1 x float> @llvm.matrix.multiply.v1f32.v1f32.v1f32(<1 x float>, <1 x float>, i32, i32, i32)

define <1 x float> @dotproduct_float_v3(<3 x float> %a, <3 x float> %b) {
; CHECK-LABEL: @dotproduct_float_v3(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = fmul <3 x float> [[A:%.*]], [[B:%.*]]
; CHECK-NEXT:    [[TMP1:%.*]] = call fast float @llvm.vector.reduce.fadd.v3f32(float 0.000000e+00, <3 x float> [[TMP0]])
; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <1 x float> poison, float [[TMP1]], i64 0
; CHECK-NEXT:    ret <1 x float> [[TMP2]]
;
entry:
  %c = tail call fast <1 x float> @llvm.matrix.multiply.v1f32.v3f32.v3f32(<3 x float> %a, <3 x float> %b, i32 1, i32 3, i32 1)
  ret <1 x float> %c
}

declare <1 x float> @llvm.matrix.multiply.v1f32.v3f32.v3f32(<3 x float>, <3 x float>, i32, i32, i32)

define <1 x float> @intrinsic_column_major_load_dot_product_float_v6(ptr %lhs_address, ptr %rhs_address) {
; CHECK-LABEL: @intrinsic_column_major_load_dot_product_float_v6(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[COL_LOAD:%.*]] = load <6 x float>, ptr [[RHS_ADDRESS:%.*]], align 4
; CHECK-NEXT:    [[TMP0:%.*]] = load <6 x float>, ptr [[LHS_ADDRESS:%.*]], align 32
; CHECK-NEXT:    [[TMP1:%.*]] = fmul <6 x float> [[TMP0]], [[COL_LOAD]]
; CHECK-NEXT:    [[TMP2:%.*]] = call fast float @llvm.vector.reduce.fadd.v6f32(float 0.000000e+00, <6 x float> [[TMP1]])
; CHECK-NEXT:    [[TMP3:%.*]] = insertelement <1 x float> poison, float [[TMP2]], i64 0
; CHECK-NEXT:    ret <1 x float> [[TMP3]]
;
entry:
  %lhs = tail call fast <6 x float> @llvm.matrix.column.major.load.v6f32.i64(ptr nonnull align 4 %lhs_address, i64 1, i1 false, i32 1, i32 6)
  %rhs = tail call fast <6 x float> @llvm.matrix.column.major.load.v6f32.i64(ptr nonnull align 4 %rhs_address, i64 6, i1 false, i32 6, i32 1)
  %result = tail call fast <1 x float> @llvm.matrix.multiply.v1f32.v6f32.v6f32(<6 x float> %lhs, <6 x float> %rhs, i32 1, i32 6, i32 1)
  ret <1 x float> %result
}

declare <6 x float> @llvm.matrix.column.major.load.v6f32.i64(ptr nonnull align 4, i64, i1, i32, i32)

define <1 x float> @LoadInst_dot_product_float_v7(ptr %lhs_address, ptr %rhs_address) {
; CHECK-LABEL: @LoadInst_dot_product_float_v7(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[LHS:%.*]] = load <7 x float>, ptr [[LHS_ADDRESS:%.*]], align 32
; CHECK-NEXT:    [[COL_LOAD:%.*]] = load <7 x float>, ptr [[RHS_ADDRESS:%.*]], align 32
; CHECK-NEXT:    [[TMP0:%.*]] = fmul <7 x float> [[LHS]], [[COL_LOAD]]
; CHECK-NEXT:    [[TMP1:%.*]] = call fast float @llvm.vector.reduce.fadd.v7f32(float 0.000000e+00, <7 x float> [[TMP0]])
; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <1 x float> poison, float [[TMP1]], i64 0
; CHECK-NEXT:    ret <1 x float> [[TMP2]]
;
entry:
  %lhs = load <7 x float>, ptr %lhs_address
  %rhs = load <7 x float>, ptr %rhs_address
  %c = tail call fast <1 x float> @llvm.matrix.multiply.v1f32.v7f32.v7f32(<7 x float> %lhs, <7 x float> %rhs, i32 1, i32 7, i32 1)
  ret <1 x float> %c
}

declare <1 x float> @llvm.matrix.multiply.v1f32.v7f32.v7f32(<7 x float>, <7 x float>, i32, i32, i32)

define <1 x double> @dotproduct_double_v6(<6 x double> %a, <6 x double> %b) {
; CHECK-LABEL: @dotproduct_double_v6(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = fmul <6 x double> [[A:%.*]], [[B:%.*]]
; CHECK-NEXT:    [[TMP1:%.*]] = call fast double @llvm.vector.reduce.fadd.v6f64(double 0.000000e+00, <6 x double> [[TMP0]])
; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <1 x double> poison, double [[TMP1]], i64 0
; CHECK-NEXT:    ret <1 x double> [[TMP2]]
;
entry:
  %c = tail call fast <1 x double> @llvm.matrix.multiply.v1f64.v6f64.v6f64(<6 x double> %a, <6 x double> %b, i32 1, i32 6, i32 1)
  ret <1 x double> %c
}

declare <1 x double> @llvm.matrix.multiply.v1f64.v6f64.v6f64(<6 x double>, <6 x double>, i32, i32, i32)

define <1 x double> @intrinsic_column_major_load_dot_product_double_v6(ptr %lhs_address, ptr %rhs_address) {
; CHECK-LABEL: @intrinsic_column_major_load_dot_product_double_v6(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[COL_LOAD:%.*]] = load <6 x double>, ptr [[RHS_ADDRESS:%.*]], align 4
; CHECK-NEXT:    [[TMP0:%.*]] = load <6 x double>, ptr [[LHS_ADDRESS:%.*]], align 64
; CHECK-NEXT:    [[TMP1:%.*]] = fmul <6 x double> [[TMP0]], [[COL_LOAD]]
; CHECK-NEXT:    [[TMP2:%.*]] = call fast double @llvm.vector.reduce.fadd.v6f64(double 0.000000e+00, <6 x double> [[TMP1]])
; CHECK-NEXT:    [[TMP3:%.*]] = insertelement <1 x double> poison, double [[TMP2]], i64 0
; CHECK-NEXT:    ret <1 x double> [[TMP3]]
;
entry:
  %lhs = tail call fast <6 x double> @llvm.matrix.column.major.load.v6f64.i64(ptr nonnull align 4 %lhs_address, i64 1, i1 false, i32 1, i32 6)
  %rhs = tail call fast <6 x double> @llvm.matrix.column.major.load.v6f64.i64(ptr nonnull align 4 %rhs_address, i64 6, i1 false, i32 6, i32 1)
  %result = tail call fast <1 x double> @llvm.matrix.multiply.v1f64.v6f64.v6f64(<6 x double> %lhs, <6 x double> %rhs, i32 1, i32 6, i32 1)
  ret <1 x double> %result
}

declare <6 x double> @llvm.matrix.column.major.load.v6f64.i64(ptr nonnull align 4, i64, i1, i32, i32)

define <1 x double> @LoadInst_dot_product_double_v7(ptr %lhs_address, ptr %rhs_address) {
; CHECK-LABEL: @LoadInst_dot_product_double_v7(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[LHS:%.*]] = load <7 x double>, ptr [[LHS_ADDRESS:%.*]], align 64
; CHECK-NEXT:    [[COL_LOAD:%.*]] = load <7 x double>, ptr [[RHS_ADDRESS:%.*]], align 64
; CHECK-NEXT:    [[TMP0:%.*]] = fmul <7 x double> [[LHS]], [[COL_LOAD]]
; CHECK-NEXT:    [[TMP1:%.*]] = call fast double @llvm.vector.reduce.fadd.v7f64(double 0.000000e+00, <7 x double> [[TMP0]])
; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <1 x double> poison, double [[TMP1]], i64 0
; CHECK-NEXT:    ret <1 x double> [[TMP2]]
;
entry:
  %lhs = load <7 x double>, ptr %lhs_address
  %rhs = load <7 x double>, ptr %rhs_address
  %c = tail call fast <1 x double> @llvm.matrix.multiply.v1f64.v7f64.v7f64(<7 x double> %lhs, <7 x double> %rhs, i32 1, i32 7, i32 1)
  ret <1 x double> %c
}

declare <1 x double> @llvm.matrix.multiply.v1f64.v7f64.v7f64(<7 x double>, <7 x double>, i32, i32, i32)